Skip to main content
POST
/
transcribe
/
status
cURL
curl --request POST \
  --url https://nano-gpt.com/api/transcribe/status \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "runId": "abc123def456",
  "cost": 123,
  "paymentSource": "<string>",
  "isApiRequest": true,
  "fileName": "<string>",
  "fileSize": 123,
  "chargedDuration": 123,
  "diarize": true
}
'
{
  "status": "pending",
  "transcription": "Speaker 1: Hello everyone. Speaker 2: Hi there!",
  "metadata": {
    "fileName": "<string>",
    "fileSize": 123,
    "chargedDuration": 123,
    "actualDuration": 123,
    "language": "<string>",
    "cost": 123,
    "currency": "<string>",
    "model": "<string>"
  },
  "words": [
    {
      "text": "<string>",
      "start": 123,
      "end": 123,
      "type": "word",
      "speaker_id": "<string>"
    }
  ],
  "diarization": {
    "segments": [
      {
        "speaker": "<string>",
        "text": "<string>",
        "start": 123,
        "end": 123
      }
    ]
  },
  "error": "<string>"
}

​
Overview

Check the status of an asynchronous transcription job (Elevenlabs-STT). Poll this endpoint to get transcription results when the job is completed.

​
Usage

This endpoint is used with the Elevenlabs-STT model which processes transcriptions asynchronously. After submitting a transcription job, you’ll receive a runId that you use to check the status. 
import requests
import time

def check_transcription_status(run_id, job_data):
    headers = {
        "x-api-key": "YOUR_API_KEY",
        "Content-Type": "application/json"
    }
    
    status_data = {
        "runId": run_id,
        "cost": job_data.get('cost'),
        "paymentSource": job_data.get('paymentSource'),
        "isApiRequest": True,
        "fileName": job_data.get('fileName'),
        "fileSize": job_data.get('fileSize'),
        "chargedDuration": job_data.get('chargedDuration'),
        "diarize": job_data.get('diarize', False)
    }
    
    response = requests.post(
        "https://nano-gpt.com/api/transcribe/status",
        headers=headers,
        json=status_data
    )
    
    return response.json()

def wait_for_completion(run_id, job_data, max_attempts=60):
    for attempt in range(max_attempts):
        result = check_transcription_status(run_id, job_data)
        status = result.get('status')
        
        if status == 'completed':
            return result
        elif status == 'failed':
            raise Exception(f"Transcription failed: {result.get('error')}")
        
        print(f"Status: {status} (attempt {attempt + 1}/{max_attempts})")
        time.sleep(5)
    
    raise Exception("Transcription timed out")

# Usage
job_data = {"runId": "abc123", "cost": 0.075, "paymentSource": "USD"}
result = wait_for_completion("abc123", job_data)
print(result['transcription'])

​
Status Values

  • pending: Job is queued for processing
  • processing: Transcription is in progress
  • completed: Transcription finished successfully
  • failed: Transcription failed (check error field)

​
Response Examples

​
Pending/Processing

{
  "status": "processing"
}

​
Completed

{
  "status": "completed",
  "transcription": "Speaker 1: Hello everyone. Speaker 2: Hi there!",
  "metadata": {
    "fileName": "meeting.mp3",
    "fileSize": 2345678,
    "chargedDuration": 2.5,
    "actualDuration": 2.47,
    "language": "en",
    "cost": 0.075,
    "currency": "USD",
    "model": "Elevenlabs-STT"
  },
  "words": [
    {
      "text": "Hello",
      "start": 0.5,
      "end": 0.9,
      "type": "word",
      "speaker_id": "speaker_0"
    }
  ],
  "diarization": {
    "segments": [
      {
        "speaker": "Speaker 1",
        "text": "Hello everyone",
        "start": 0.5,
        "end": 1.5
      }
    ]
  }
}

​
Failed

{
  "status": "failed",
  "error": "Audio file could not be processed"
}

Authorizations

​
x-api-key
string
header
required

Body

application/json

Status check parameters including runId from the initial transcription request

​
runId
string
required

Unique identifier for the transcription job

Example:

"abc123def456"

​
cost
number

Cost of the transcription (from initial response)

​
paymentSource
string

Payment source used (from initial response)

​
isApiRequest
boolean

Whether this is an API request (from initial response)

​
fileName
string

Original file name (from initial response)

​
fileSize
integer

File size in bytes (from initial response)

​
chargedDuration
number

Duration charged for billing (from initial response)

​
diarize
boolean

Whether speaker diarization is enabled (from initial response)

Response

Transcription status response

​
status
enum<string>
required

Current status of the transcription job

Available options:
pending,
processing,
completed,
failed
​
transcription
string

The transcribed text (available when status is 'completed')

Example:

"Speaker 1: Hello everyone. Speaker 2: Hi there!"

​
metadata
object

Transcription metadata (available when status is 'completed')

​
words
object[]

Word-level timestamps and speaker information (Elevenlabs-STT only)

​
diarization
object

Speaker diarization results (when enabled)

​
error
string

Error message (available when status is 'failed')